© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 15223
    Prev
    Next
    INDEX
    Explanations

    references to software features and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FIG
    -0.68
     FIG
    -0.57
    
    -0.53
    RTDA
    -0.52
     protoimpl
    -0.50
     հղումներ
    -0.49
    Hentet
    -0.48
     keselamatan
    -0.48
    XmlAccessType
    -0.47
     irmã
    -0.45
    POSITIVE LOGITS
    <h4>
    2.08
    <h5>
    1.51
    </h4>
    1.21
    <h6>
    1.20
    ####
    0.85
    subsubsection
    0.84
     ####
    0.75
    "].
    0.71
    0.70
    '].
    0.66
    Activations Density 0.090%

    No Known Activations